shell

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description explains dry-run safety and sandbox execution, adding context beyond annotations (destructiveHint: true, openWorldHint: true). No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences that front-load the key purpose and execution modes. No fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description covers dry-run and execution behavior. Could mention potential destructive consequences explicitly, but sandbox implies safety.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3 applies. Description does not add new meaning beyond schema; the dry-run context is already in schema description. Parameter info is adequate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it generates and optionally executes shell commands via Gemini, with a specific dry-run mode. It differentiates from sibling tools which are unrelated (e.g., web-search, brainstorm).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says dry-run default and when to set dryRun=false for execution. No explicit exclusions or alternatives, but sibling tools are distinct, so context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.